Edge-Convolution Point Net For Semantic Segmentation Of Large-Scale Point Clouds. Jhonatan Contreras and Joachim Denzler. IEEE International Geoscience and Remote Sensing Symposium (IGARSS).2019.
Abstract: We propose a deep learning-based framework which can manage large-scale point clouds of outdoor scenes with high spatial resolution. Analogous to Object-Based Image Analysis (OBIA), our approach segments the scene by grouping similar points together to generate meaningful objects. Later, our net classifies segments instead of individual points using an architecture inspired by PointNet, which applies Edge convolutions, making our approach efficient. Usually, Light Detection and Ranging (LiDAR) data do not come together with RGB information. This approach was trained using both RBG and RGB+XYZ information. In some circumstances, LiDAR data presents patterns that do not correspond to the surface object. This mainly occurs when objects partially block beans of light, to address this issue, normalized elevation was included in the analysis to make the model more robust.
An Improved Variant of the Conventional Harmony Search Algorithm. Jhonatan Contreras and Ivan Amaya and Rodrigo Correa. Applied Mathematics and Computation.227 (1):pages 821-830.2014.
Abstract: The Harmony Search algorithm (HS) has been used for optimization in different fields, and despite the relative short time it has been around, it already has many variants. This article presents a new modification of HS, based on variable parameters, which is able to yield better results than previously reported data, and with the additional benefit of not requiring prior knowledge of the maximum number of iterations. In this research, a comparison is made with the original HS algorithm, and with its improved version (i.e. IHS), finding that the proposed variants not only reduce convergence time of the algorithm, but they also increase its precision. Some commonly used benchmark functions were used as a testing scenario, and the performance of the novel approach is evaluated for an objective function in up to 1000D, where it was found to converge appropriately. These findings are important since they indicate that the proposed version could be used for different kinds of optimization problems, thus allowing a broader use of the HS algorithm.